Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of famous individuals or specific topics in various fields, potentially related to current events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific entities, often in the context of questions or discussions about them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.89
    details
    -0.77
    edIn
    -0.72
    çīĪ
    -0.69
    roups
    -0.68
    çļ
    -0.68
    irts
    -0.67
    ":"","
    -0.67
    ook
    -0.66
    udes
    -0.65
    POSITIVE LOGITS
     supposed
    1.27
     gonna
    1.06
     worth
    1.01
     able
    1.00
     really
    1.00
     contagious
    0.98
     ready
    0.97
     going
    0.96
     aware
    0.95
     REALLY
    0.94
    Act Density 0.114%

    No Known Activations